Authorizing distributed task processing in a distributed storage network

Patent metadata

Field	Value
Publication number	US-9430286-B2
Application number	US-201313865659-A
Country	US
Kind code	B2
Filing date	Apr 18, 2013
Priority date	Dec 12, 2011
Publication date	Aug 30, 2016
Grant date	Aug 30, 2016

Abstract

A method begins by a distributed storage (DS) processing module transmitting a set of requests to a set of DS units regarding a set of data elements and receiving a set of respective requests from the set of DS units. When the set of respective requests is in accordance with a current distributed task/data responsibility allocation period, the method continues with the DS processing module issuing a set of responses to the set of DS units. The method continues with the DS processing module receiving a set of respective responses from the set of DS units. When the set of received respective responses is in accordance with the current distributed task/data responsibility allocation period, the method continues with the DS processing module processing the set of received respective responses in accordance with the current distributed task/data responsibility allocation period to produce one of a set of results.

First claim

What is claimed is:

1. A method for execution by a set of distributed storage (DS) units, the method comprises:
transmitting, by each DS unit of the set of DS units, a set of requests to other DS units of the set of DS units, wherein a request of the set of requests includes requesting a response regarding a respective data element of a set of data elements from a respective one of the other DS units, and wherein the set of requests are generated in accordance with a current distributed task/data responsibility allocation period, wherein, collectively, the set of DS units contains a plurality of sets of data elements;
receiving, by the each DS unit, a respective request from each of the other DS units such that the each DS unit receives a set of respective requests from the other DS units;
when each of the set of respective requests is in accordance with the current distributed task/data responsibility allocation period:
generating, by the each DS unit, a response to each respective request of the set of respective requests to produce a set of responses; and
sending, by the each DS unit, the set of responses to the other DS units;

receiving, by the each DS unit, a respective response from each of the sets of responses from the other DS units such that the each DS unit receives a set of respective responses from the other DS units; and
when the set of respective responses is in accordance with the current distributed task/data responsibility allocation period, processing, by the each DS unit, the set of respective responses in accordance with the current distributed task/data responsibility allocation period to produce one of a set of results such that the set of DS units produces the set of results regarding the plurality of sets of data elements.

2. The method of claim 1 , wherein the processing the set of respective responses comprises at least one of:
performing, by the each DS unit, an integrity check on data elements associated with the set of respective responses to produce the one of the set of results, wherein the set of results provides an integrity indication for the plurality of sets of data elements;
verifying, by the each DS unit, a read request based on the data elements associated with the set of respective responses to produce the one of the set of results, wherein the set of results provides a validity indication for a read operation regarding the plurality of sets of data elements; and
verifying, by the each DS unit, a write request based on the data elements associated with the set of respective responses to produce the one of the set of results, wherein the set of results provides a validity indication for a write operation regarding the plurality of sets of data elements.

3. The method of claim 1 further comprises:
when one of the set of respective requests is not in accordance with the current distributed task/data responsibility allocation period, indicating, by the each DS unit, as potentially compromised, the respective one of the other DS units corresponding to the one of the set of respective requests not in accordance with the current distributed task/data responsibility allocation period.

4. The method of claim 3 further comprises at least one of:
determining, by the each DS unit, that the one of the set of respective requests is not in accordance with the current distributed task/data responsibility allocation period when the respective one of the other DS units corresponding to the one of the set of respective requests is not an anticipated requesting DS unit in accordance with the current distributed task/data responsibility allocation period;
determining, by the each DS unit, that the one of the set of respective requests is not in accordance with the current distributed task/data responsibility allocation period when the one of the set of respective requests is not an anticipated request in accordance with the current distributed task/data responsibility allocation period; and
determining, by the each DS unit, that the one of the set of respective requests is not in accordance with the current distributed task/data responsibility allocation period when the one of the set of respective requests is a second request by the respective one of the other DS units.

5. The method of claim 1 further comprises:
when one of the set of respective responses is not in accordance with the current distributed task/data responsibility allocation period, indicating, by the each DS unit, as potentially compromised, the respective one of the other DS units corresponding to the one of the set of respective responses not in accordance with the current distributed task/data responsibility allocation period.

6. The method of claim 5 further comprises at least one of:
determining, by the each DS unit, that the one of the set of respective responses is not in accordance with the current distributed task/data responsibility allocation period when the respective one of the other DS units corresponding to the one of the set of respective responses is not an anticipated responding DS unit in accordance with the current distributed task/data responsibility allocation period;
determining, by the each DS unit, that the one of the set of respective responses is not in accordance with the current distributed task/data responsibility allocation period when the one of the set of respective responses is not an anticipated response in accordance with the current distributed task/data responsibility allocation period; and
determining, by the each DS unit, that the one of the set of respective responses is not in accordance with the current distributed task/data responsibility allocation period when the one of the set of respective responses is a second response by the respective one of the other DS units.

7. The method of claim 1 , wherein the current distributed task/data responsibility allocation period comprises at least one of:
a time varying allocation of tasks among the set of DS units;
a time varying allocation of data elements to process;
a time varying allocation of permissible requests; and
a time varying allocation of permissible responses.

8. A distributed storage (DS) module of each DS unit of a set of DS units, the DS module comprises:
a first module, when operable within a computing device, causes the computing device to:
transmit a set of requests to other DS units of the set of DS units, wherein a request of the set of requests includes requesting a response regarding a respective data element of a set of data elements from a respective one of the other DS units, and wherein the set of requests are generated in accordance with a current distributed task/data responsibility allocation period, wherein, collectively, the set of DS units contains a plurality of sets of data elements;

a second module, when operable within the computing device, causes the computing device to:
receive a respective request from each of the other DS units to produce a set of respective requests; and
when each of the set of respective requests is in accordance with the current distributed task/data responsibility allocation period:
generate a response to each respective request of the set of respective requests to produce a set of responses; and
send the set of responses to the other DS units; and

a third module, when operable within the computing device, causes the computing device to:
receive a respective response from each of the sets of responses from the other DS units such that the each DS unit receives a set of respective responses from the other DS units; and
when the set of respective responses is in accordance with the current distributed task/data responsibility allocation period, process the set of respective responses i

Assignees

• Cleversafe Inc
• IBM

Inventors

• Volvovski Ilya
• Resch Jason K

Classifications

• H03M13/09

  Error detection only, e.g. using cyclic redundancy check [CRC] codes or single parity bit · CPC title

• G06F11/1092

  Rebuilding, e.g. when physically replacing a failing disk · CPC title

• G06F2211/1028

  Distributed, i.e. distributed RAID systems with parity · CPC title

• H04L67/1097

  for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS] · CPC title

• G06F11/1076 Primary

  Parity data used in redundant arrays of independent storages, e.g. in RAID systems · CPC title